An speech and face fusion recognition method based on fuzzy integral

摘要

Studies show that multiple modal biometric systems for small-scale populations perform better than single modal biometric systems for robots's recognition. This paper establishes a new fusion method for multiple biometric feature identification which combines visual with auditory information. Before the fusion, speaker recognition based on vector quantization and face recognition based on sparse representation get their single modal similarity and accepted rate respectively, then the similarity is normalized to get the matching score. Finally, fuzzy measure and fuzzy integrals are used for the fusion of speaker recognition and face recognition to obtain the matching result. In the actual environment, the mobile robot utilize this method to realize the recognition. The result of experiment indicates that the performance is better than single modal recognition.